Compare

Gemma-4-26b-A4b-IT vs Claude Haiku 4.5

Pricing per million tokens, context window, capabilities — pulled from each provider's public docs. All 2 are available via the same AIgateway OpenAI-compatible endpoint; flip the model string to switch.

Search2/4
Gemma-4-26b-A4b-IT
google/gemma-4-26b-a4b-it
Claude Haiku 4.5
anthropic/claude-haiku-4.5
Provider
Google
Anthropic
Family
Gemma
Claude 4
Modality
text
text
Context window
131,072 tok
200,000 tok
Max output
4,096 tok
8,192 tok
Released
2026-04-02
2026-05-22
License
Open-weight
Proprietary
Input price
$0.340 /1M
$1.00 /1M
Output price
$0.560 /1M
$5.00 /1M
Cache read
$0.100 /1M
Cache write
$1.25 /1M
Tools
yes
Streaming
yes
yes
Vision
yes
yes
JSON mode
yes
Reasoning
Prompt caching
yes
Batch API
Try it
Open in playground →
Open in playground →
Gemma-4-26b-A4b-IT
google/gemma-4-26b-a4b-it
Full spec →

Gemma 4 is Google's most intelligent family of open models, built from Gemini 3 research to maximize intelligence-per-parameter.

Strengths
  • General-purpose chat
  • Long context
  • Tool use
Use cases
ChatbotsContent generationAgentic workflows
Claude Haiku 4.5
anthropic/claude-haiku-4.5
Full spec →

Claude Haiku 4.5 delivers similar levels of coding performance at one-third the cost and more than twice the speed of larger models.

Strengths
  • Fastest Claude
  • Cheap enough for per-token workloads
  • Still supports tools + vision
Use cases
ClassifiersRoutingHigh-throughput chatReal-time agents

Benchmarks

Gemma-4-26b-A4b-IT
Claude Haiku 4.5
HumanEval
85.2
MMLU
80.1

Source: each provider's published benchmarks. Higher is better. Run an eval to compare on your own data.

Compare with another

GPT-5.4 Mini vs Claude Haiku 4.5
openai/gpt-5.4-mini · anthropic/claude-haiku-4.5
Claude Haiku 4.5 vs Gemini 3 Flash
anthropic/claude-haiku-4.5 · google/gemini-3-flash
Claude Opus 4.8 vs Gemma-4-26b-A4b-IT
anthropic/claude-opus-4.8 · google/gemma-4-26b-a4b-it
Claude Opus 4.8 vs Claude Haiku 4.5
anthropic/claude-opus-4.8 · anthropic/claude-haiku-4.5
MiniMax M3 vs Gemma-4-26b-A4b-IT
minimax/m3 · google/gemma-4-26b-a4b-it
MiniMax M3 vs Claude Haiku 4.5
minimax/m3 · anthropic/claude-haiku-4.5
Gemini 3.1 Pro vs Gemma-4-26b-A4b-IT
google/gemini-3.1-pro · google/gemma-4-26b-a4b-it
Gemini 3.1 Pro vs Claude Haiku 4.5
google/gemini-3.1-pro · anthropic/claude-haiku-4.5
Claude Sonnet 4.6 vs Gemma-4-26b-A4b-IT
anthropic/claude-sonnet-4.6 · google/gemma-4-26b-a4b-it
SWITCH BETWEEN THEM

One key, all 2, one line different.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.aigateway.sh/v1",
    api_key="sk-aig-...",
)

# Gemma-4-26b-A4b-IT
client.chat.completions.create(
    model="google/gemma-4-26b-a4b-it",
    messages=[{"role":"user","content":"hello"}],
)

# Claude Haiku 4.5
client.chat.completions.create(
    model="anthropic/claude-haiku-4.5",
    messages=[{"role":"user","content":"hello"}],
)
Get an AIgateway keyRun an eval on these →